PixAI-Mitgliedschaft
PixAI
PixAI
Generate
Sign in
Startseite
Generation
Modelle
Studio
NEW
Wettbewerb
Mit Mio.2 erstellen
Toolbox
NEW
PixAI-Dokument

SDXL

MiaoMiao Pixel

Erstellen

  • KI-Bildgenerator
  • KI-Animationsgenerator
  • Toolbox
  • Themengeneratoren
  • LoRA trainieren
  • Mio.2 Agent
  • Studio

Entdecken

  • Angesagte Tags
  • Rangliste
  • Modell-Marktplatz
  • Wettbewerb
  • Nachricht

Über uns

  • PixAI-Dokument
  • So verwendest du PixAI
  • Tsubaki.2
  • Mio kennenlernen
  • Inhaltsregeln

Preise & Hilfe

  • Mitgliedschaft
  • Credit-Pakete
  • Kontakt

Mobile App

  • Hol dir die PixAI-App
  • App-Store
  • Google PlayStore
© 2026 PixAI
  • Nutzungsbedingungen
  • Datenschutzbestimmungen
  • Urheberrechtsrichtlinie
  • Attributions
  • Gesetz über bestimmte kommerzielle Transaktionen
MiaoMiao Pixel - AI Model cover image
Hochgeladen am
18.10.2025, 00:28
Verwendet
12.6k
Bewertungen
Exzellent  (7)
Sampling-Schritte

30

Sampling-Methode

Euler a

CFG scale

6

Negativ

lowres,(bad),limb asymmetry,bad feet,text,error,fewer,extra,missing,worst quality,jpeg artifacts,low quality,watermark,unfinished,displeasing,oldest,early,chromatic aberration,signature,simple_background,artistic error,username,scan,[abstract],english text,

Berechtigungen
  • Bildgenerierung und -freigabe erlauben
  • Nutzern erlauben, dieses Modell herunterzuladen
  • Gewerbliche Nutzung

Empfohlene LoRAs

LCM&TurboMix LoRA (eular a.fix) XL - AI Model cover image

Benutzer-LoRA

LCM&TurboMix LoRA (eular a.fix) XL
10.62k
Detailed anime style - Illustrious V2.0 - AI Model cover image

Benutzer-LoRA

Detailed anime style - Illustrious V2.0
1.82k
Hyper SDXL - AI Model cover image

Benutzer-LoRA

Hyper SDXL
8.57k
2B (NieR: Automata) - Comission LoRA PonyXL [NSFW Support] - AI Model cover image

Benutzer-LoRA

2B (NieR: Automata) - Comission LoRA PonyXL [NSFW Support]
133

Beschreibung

MiaoMiao Pixel 是个超好玩的像素画 模型 !不管你是想设计复古游戏角色、制作卡通头像,还是随便涂鸦点有趣图案,点点屏幕就能生成超有感觉的像素风图片。它不像那些复杂的像素绘图软件,主打一个简单有趣,操作也超简单,随便输入几个关键词,就能得到超酷的作品,特别适合制作特别的创意! 虽然有人说 像素没必要训练大模型 训练lora就足够了但是我认为有一个专一的大模型效果可能会更稳定避免Lora搭配错误的大模型 不兼容导致效果不佳QQ群:⬅️点击加群 QQ中转群:926213169 Telegram: https://t.me/+3bmWl5i4SwZmNjA1Model Output ParametersRecommended upscaling algorithm放大算法(Amplification algorithm) Put in path :.\models\ESRGANScheduler euler aSteps 30CFG Scale 6Model Recommended Resolution 768X1280 (模型不需要高清修复)Positive Prompt (default ){此处添加提示词 Add Prompt here},masterpiece, best quality, absurdres, newest, very aesthetic, amazing quality,highres,sensitiveNegative Promptlowres,(bad),bad feet,text,error,fewer,extra,missing,worst quality,jpeg artifacts,low quality,watermark,unfinished,displeasing,oldest,early,chromatic aberration,signature,artistic error,username,scan,[abstract],english text,shiny_skin,Model Usage Statement1. You are not allowed to host this model and its derivative versions (such as fusion model versions) on websites/applications that plan to earn income or donate. If you need to use this model and its derivative versions for commercial purposes (such as generative services, selling images, using images for public publication on short video platforms, etc.), please contact me through the website2. You are not allowed to directly sell images generated by this model, unless you have made sufficient manual modifications to the image so that it can be fully recognized as your personal work in a legal sense. If you violate this provision, all legal consequences resulting from it shall be borne by you personally, and I am not responsible.3. You cannot use this model to intentionally create or share illegal or harmful content for dissemination and output. Please abide by public order and good ethics, and

Kommentare